The lecture will take place on Monday 11th June, at 16:00 hours, during the Symposium on Conformal & Probabilistic Prediction with Applications (COPA 2018) in Maastricht, The Netherlands.
Please register your attendance here.
In the talk I will consider Teacher-Student interaction in learning processes. I will introduce a new learning paradigm, called Learning Using Statistical Invariants (LUSI), which is different from the classical one.
In the classical paradigm, a learning machine constructs, using data, a classification or regression function that minimizes the expected loss; it is thus data-driven learning. In the LUSI paradigm, in order to construct the desired classification or regression function using both data and Teacher's input, the learning machine computes statistical invariants that are specific for the problem, and then minimizes the expected loss in a way that preserves these invariants; it is thus both data- and intelligence-driven learning.
From a mathematical point of view, methods of the classical paradigm employ mechanisms of strong convergence of approximations to the desired function, whereas methods of the new paradigm employ both strong and weak convergence mechanisms. This can significantly increase the rate of convergence.
An invitation to give a Kolmogorov Lecture acknowledges life-long research contributions to one of the fields initiated or transformed by Kolmogorov.
Prof. Merton won the Nobel Prize in Economic Sciences in 1997, for his pioneering contributions to continuous-time finance, and the Black–Scholes formula.
Prof. Sinai is well-known for his work on dynamical systems, which have provided the groundwork for advances in the physical sciences.
Prof. Rissanen was the inventor of the minimum description length principle and practical approaches to arithmetic coding for lossless data compression.
Prof. Martin-Löf is internationally renowned for his work on the foundations of probability, statistics, mathematical logic, type theory which has influenced computer science.
Prof. Levin is well-known for his work in randomness in computing, algorithmic complexity and intractability, foundations of mathematics and computer science.
Andrei Kolmogorov (1903-1987) made fundamental contributions to probability theory, statistics, analysis, mathematical logic, the theory of algorithms, information theory, and the theory of dynamic systems. His discoveries completely changed many of these areas. He was a brilliant teacher, with many of his students and followers continuing his groundbreaking work.
In 1998, Royal Holloway, University of London, established the Computer Learning Research Centre under the directorship of Alexander Gammerman. Professor Gammerman and the Centre's Deputy Director, Vladimir Vovk, were joined by several outstanding researchers in the field of Kolmogorov Complexity.
To celebrate the centenary of Kolmogorov's birth (25 April 1903), the Computer Learning Research Centre proposed the establishment of the University of London Kolmogorov Lecture and Medal. This decision was approved in 2002, and the Lectures have been held since then at Royal Holloway, University of London.
The Organising and Programme Board consists of members from several Colleges within the University of London. The Advisory Board consists of some of the previous Kolmogorov speakers who give advice on future speaker nominations.
Professor of Computer Science, Co-Director of Royal Holloway's Computer Learning Research Centre and Fellow of the Royal Statistical Society.
Professor of Computer Science, Co-Director of Royal Holloway's Computer Learning Research Centre, Fellow the Royal Statistical Society.
Emeritus Professor of Mathematics at Imperial College, London, Fellow of the British Academy and has served (twice) as President of the Royal Statistical Society.
Emeritus Professor of Mathematical Sciences, Queen Mary University of London.